{"id":"https://openalex.org/W3215413293","doi":"https://doi.org/10.1007/978-3-030-91669-5_30","title":"Evaluating the Robustness of Embedding-Based Topic Models to OCR Noise","display_name":"Evaluating the Robustness of Embedding-Based Topic Models to OCR Noise","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3215413293","doi":"https://doi.org/10.1007/978-3-030-91669-5_30","mag":"3215413293"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-91669-5_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-91669-5_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/5854622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064201950","display_name":"Elaine Zosa","orcid":"https://orcid.org/0000-0003-2482-0663"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Elaine Zosa","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0003-2482-0663","affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085451602","display_name":"Stephen Mutuvi","orcid":"https://orcid.org/0000-0002-3067-9806"},"institutions":[{"id":"https://openalex.org/I327535454","display_name":"Multimedia University of Kenya","ror":"https://ror.org/028r4zr88","country_code":"KE","type":"education","lineage":["https://openalex.org/I327535454"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR","KE"],"is_corresponding":false,"raw_author_name":"Stephen Mutuvi","raw_affiliation_strings":["L3i Laboratory, University of La Rochelle, La Rochelle, France","Multimedia University of Kenya, Nairobi, Kenya"],"raw_orcid":"https://orcid.org/0000-0002-3067-9806","affiliations":[{"raw_affiliation_string":"L3i Laboratory, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"Multimedia University of Kenya, Nairobi, Kenya","institution_ids":["https://openalex.org/I327535454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088458735","display_name":"Mark Granroth-Wilding","orcid":"https://orcid.org/0000-0002-6020-5687"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mark Granroth-Wilding","raw_affiliation_strings":["Silo AI, Helsinki, Finland","University of Helsinki, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Silo AI, Helsinki, Finland","institution_ids":[]},{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["L3i Laboratory, University of La Rochelle, La Rochelle, France"],"raw_orcid":"https://orcid.org/0000-0001-6160-3356","affiliations":[{"raw_affiliation_string":"L3i Laboratory, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.7953,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88052121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8434604406356812},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8345257043838501},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6132766008377075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6116599440574646},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6087455749511719},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5740170478820801},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5195153951644897},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4613649249076843},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45777270197868347},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4045770764350891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40352141857147217},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33952367305755615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434604406356812},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8345257043838501},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6132766008377075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6116599440574646},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6087455749511719},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5740170478820801},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5195153951644897},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4613649249076843},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45777270197868347},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4045770764350891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40352141857147217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33952367305755615},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-030-91669-5_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-91669-5_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:zenodo.org:5854622","is_oa":true,"landing_page_url":"https://zenodo.org/record/5854622","pdf_url":"https://zenodo.org/record/5854622","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"pmh:oai:HAL:hal-03480518v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03480518","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Hao-Ren Ke; Chei Sian Lee; Kazunari Sugiyama. Towards Open and Trustworthy Digital Societies. 23rd International Conference on Asia-Pacific Digital Libraries, ICADL 2021, Virtual Event, December 1\u20133, 2021, Proceedings, 13133, Springer, pp.392-400, 2021, Lecture Notes in Computer Science, 978-3-030-91668-8. &#x27E8;10.1007/978-3-030-91669-5_30&#x27E9;","raw_type":"Book sections"},{"id":"pmh:oai:helda.helsinki.fi:10138/337045","is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/337045","pdf_url":null,"source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference contribution"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:5854622","is_oa":true,"landing_page_url":"https://zenodo.org/record/5854622","pdf_url":"https://zenodo.org/record/5854622","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3215413293.pdf"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1601566332","https://openalex.org/W1614298861","https://openalex.org/W1880262756","https://openalex.org/W1990871427","https://openalex.org/W2038043464","https://openalex.org/W2122172122","https://openalex.org/W2141056424","https://openalex.org/W2150102617","https://openalex.org/W2250539671","https://openalex.org/W2250753706","https://openalex.org/W2900753330","https://openalex.org/W2964117810","https://openalex.org/W2968567788","https://openalex.org/W2981601816","https://openalex.org/W2986829274","https://openalex.org/W3045464143"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W4291700620","https://openalex.org/W4317422773"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
